Custom agents

AI-native infinite-canvas design tool: describe an app, get multi-screen HTML designs on an infinite canvas, click through them as a prototype, and let your local coding agent read and write the canvas over MCP.

TMX is a modern desktop terminal client for SSH workflows, built on Electron + React. It bundles a real persistent terminal (node-pty / ssh2 / xterm.js), a host manager, SFTP, snippets, an AI copilot and a built-in MCP server into a single cross-platform app (macOS / Windows / Linux).

An AI-assisted newsroom workflow system for event tracking, evidence organization, approval chains, correction handling, and post-publication monitoring.

RustSBI Specialized Domain Knowledge Quiz LLM

Implementation of EMNLP 2017 Paper "Natural Language Does Not Emerge 'Naturally' in Multi-Agent Dialog" using PyTorch and ParlAI

Zero Graph – Minimalist LLM framework designed for AI Agent programming

🌥 Cloud-native framework for developing pluggable service agents

Go implementation of @qdrant/fastembed.

Needle MCP Server for easy RAG.Long-term memory for LLMs.

AI-powered knowledge management without vector embeddings. Built upon Claude Agent SDK, File system based, Agent driven. Maybe slower, but results are much more reliable!

A persistent, daemon-based multi-agent system that leverages opencode to automatically discover, plan, implement, and review code changes across a codebase.

Official Oxylabs MCP integration

Self-Reflection in LLM Agents: Effects on Problem-Solving Performance

Inpact is an open-source AI-powered platform designed to connect content creators, brands, and agencies through data-driven insights. By leveraging Generative AI (GenAI), audience analytics, and engagement metrics, Inpact ensures highly relevant sponsorship opportunities for creators while maximizing ROI for brands investing in influencer marketing

[NeurIPS 2025 D&B] VIKI‑R: Coordinating Embodied Multi-Agent Cooperation via Reinforcement Learning

The AVR Infrastructure project is designed to launch the Agent Voice Response application, which will start the Core, ASR, LLM, and TTS services integrated with Asterisk Audiosocket.

AI-powered Costco Receipt Scanner & Price Match Agent. Scans receipts, finds price adjustments, emails weekly reports.

A comprehensive steganography framework for embedding and extracting agentic commands in audio and video media using ultrasonic frequencies. This project provides tools for covert communication and command transmission through multimedia channels.

DoctorAgent-RL: A Multi-Agent Collaborative Reinforcement Learning System for Multi-Turn Clinical Dialogue

Set up and improve harness engineering (AGENTS.md, docs/, lint rules, eval systems, project-level prompt engineering) for AI-agent-friendly codebases. Triggers on: new/empty project setup for AI agents, AGENTS.md or CLAUDE.md creation, harness engineering questions, making agents work better on a codebase.

An AI-powered cybersecurity agent inspired by Claude Agent SDK, designed exclusively for defensive security operations.

Automated Benchmarking of LLM Agents on Real-World Software Security Tasks [NeurIPS 2025]

A kit for building with AI agents and also the engineering patterns around it.

就算有一套完全自动赚钱的工具，你也会经常盯着它。你跟专业交易员对比，差别在于是否看得懂。而EasyDeal 就是解决这个问题的一套框架，提供一组MCP工具，接入 openclaw、Claude Code, Fay等agent后，在MT5交易环境可以协同各种策略工作，监控策略的执行、为你解答各种问题、指导你做出突发处理，甚至直接帮你修改策略代码。

Hybrid memory system for OpenClaw using Graphiti temporal knowledge graph

FSPEC: The Spec-Driven, Multi-Agent Harness. It is infrastructure for the "Dark Factory" - the emerging model of fully autonomous software development where AI agents handle all implementation while humans focus on defining what to build and why.

A practical framework for AI-Assisted Research in Mathematics and Machine Learning

Let your AI Agent review your iOS/Android apps for appstore policy & security bugs with ipaShip's web app, cli, mcp or claude-skill with safety hooks layer any any llm agent you use - loopin fixes in dev stage only no more waits till submissions.

CAPTCHA proves you're human. HATCHA proves you're not.

SDK, skills, and examples for Inkbox: give AI agents a persistent identity with email, phone number, and internet address

Turn Claude/Codex into geospatial analytics agent.

Claude Code / Codex / AI configs for the expert Solana builder. CLAUDE.md, agents, commands, hooks, rules, skills and settings across Web, Anchor, Pinnochio, Unity, Mobile, security and more.

AI-powered software development system that automates the entire lifecycle from requirements analysis to code delivery through specialized agent collaboration.

Agent and LLM API performance monitoring via network packet probe. Measures performance of OpenClaw, Claude, Codex, DeepAgents and more — deployed on the provider side, no SDK changes required.

World's fastest and most compact embedded vector database: exact by default, multimodal, local-first, and GPU-accelerated

WeChat/微信 local chat history MCP server for macOS agents. Read messages, contacts, media, favorites, transfers, red packets, Moments and full-text search from local WeChat 4.x data.

AI Agent 面试知识库：覆盖 LLM、Prompt、RAG、MCP、Tool Use、Agent 架构、Multi-Agent、LangGraph、Claude Code、Codex CLI、工程化评估、安全与源码解析。

"AI 桌面管家 · 多 Agent 协作编排 · 一句话调动团队完成复杂任务

An autonomous Site Reliability Engineering (SRE) and DevOps agent for Kubernetes with deterministic log analysis.

Enhanced MCP server for Godot 4.5-4.7: 33 tools / 199 actions, 3-layer architecture (headless + editor + game bridge), secure sandbox, recording & frame-verify, cross-version CI.

MCP server: repo map, code search, and token-aware context packs for AI coding agents

面向 AI 上下文管理的 Agent Skill：为 Codex 上下文管理、Cursor 上下文切换和 Claude 上下文管理提供跨窗口续接，用 Git 保存可验证的功能说明与变更记录。AI coding context management and agent handoffs.

Bridge Deepseek-harness into Claude Code for review, critique, delegation, and session import.

The $0 AI Empire Playbook — 180 scheduled jobs, 43 free LLM lanes, and the failure classes that almost killed it. Free tiers only.

Pi coding agent extensions with code intelligence (LSP + Tree-sitter AST), semantic refactoring, code review, web/Context7 docs, and ask-user forms.

OpenClaw Companion / OpenClaw 中文助手：中英双语、安全编排官方 OpenClaw 安装、配置、检查、升级、备份与诊断。社区项目，非官方。

ApocData · AI-native financial database for China A-share market. Drop-in Skill / MCP for Claude,ChatGPT, Qwen, Kimi, DeepSeek agents.

VetarAI 是一款全原生 Swift 的本地桌面应用：多 Agent 协作、可视化工作流、拉模式知识仓库+本地语义检索、多模型超级工作室、CU 电脑操作。数据保存在本地磁盘。

MCP server for AI-powered GitHub project management — 20 tools, 169 actions, agent swarm orchestration, GitHub Actions/Releases/Branches, MCP Resources & Prompts, PRD-to-issues pipeline

Alan's Way: a Mac app where your Hermes bots drive their own browser tabs on your Mac and a cloud VPS, with Telegram alongside and handoff between the two.

Local-first macOS app that copies Discord trading signals into Alpaca accounts, with a risk-limited engine, an AI assistant, and English or 简体中文. Developer preview.

Agent skills that make real-time game VFX: procedural Effekseer effects, video-model flipbooks, or both, played in Godot and Unity (Claude Code, Codex and other Agent Skills hosts).

A simple project for enabling LLM agents to use tools.

[ICCV 2023] ADAPT: Efficient Multi-Agent Trajectory Prediction with Adaptation

Dialogflow agent fulfillment PHP library supporting v1 & v2

Arena: A General Evaluation Platform and Building Toolkit for Single/Multi-Agent Intelligence. AAAI 2020.

Neural network-based (NN) Model Predictive Control (MPC) algorithm to control a multi-agent system (MAS) with stochastic communication topology.

AI Agent Simulation generates Minecraft Settlements

📚 2025 AI Engineering Reading List - 120+ curated AI research papers covering LLMs, Multimodal, RAG, Agents, Diffusion Models and more

Simplified Action Decoder for Deep Multi-Agent Reinforcement Learning

Spring Boot 기반 대화형 Chat Bot Supported Framework.

Manage persistent AI bots with a terminal dashboard, web UI, and declarative configuration.

A+ Grade AI Agent Security Framework - Military-grade protection against prompt injection, command injection, and Unicode bypass attacks

Systematic evaluation framework that automatically rates overthinking behavior in large language models.

Backplane Development Framework and Server hosting Choria Agents, Networks, Federations and Streaming Data

A modern, all-in-one competitive programming environment. Solve Codeforces problems with a built-in IDE, Whiteboard, and Custom Judge—no more tab switching.

On-device computer use agent that runs fully in the background 🪄

pytorch를 사용하여 텍스트 전처리부터 RAG, 에이전트, LLM 파인튜닝을 정리한 Deep Learning NLP 저장소입니다.

CLI tool for LLM agents to build and maintain personal knowledge bases

Agent-centric social network and interoperability dApp framework

Automated benchmarking of Retrieval-Augmented Generation (RAG) systems

Devr.AI is an advanced AI-powered Developer Relations (DevRel) assistant designed to revolutionize open-source community management. By integrating with platforms like Discord, Slack, GitHub, and Discourse, Devr.AI functions as a virtual DevRel advocate that helps maintainers engage with contributors and streamline onboarding processes.

Enterprise-grade PowerShell abstraction layer for 15+ GenAI providers. Standardized interface for model benchmarking, tool-calling, and high-performance LLM integration

PCLA: A framework for testing autonomous agents in the CARLA simulator

Prevent accidental PII leakage in LLM prompts before they hit the model.

One .agents source of truth to sync MCP servers, skills, and instructions across Codex, Claude Code, Gemini CLI, Cursor, Copilot, and Antigravity.

Evidence-based decision framework for selecting the right Microsoft AI technology (M365 Copilot, Copilot Studio, Azure AI Foundry, Agent Service) for your business needs

Official agent skills for coding agents working with the Mastra AI framework

Credential gateway for AI agents. Log in once via Oauth2 or API Key. Every agent stays authenticated — headless, no SaaS, agents never see your credentials.

Tor/Dark Web access skill for AI agents (OpenCode & Claude Code). Search 12 dark web engines, spider .onion sites, extract IOCs. Orchestrator-conductor architecture — zero external LLM deps.

MCP server for reading and writing HWP/HWPX (Korean Hangul) documents — built on rhwp. 34 tools, Claude/Cursor/ChatGPT compatible.

Create motion-graphics videos from natural-language using Hyperframes. Researches topics, explains GitHub repos, renders the result.

The Model Context Environment Controller is eyes, hands, and a safe front door for agents on Windows; and the same battle-tested remote control for smart-home systems.

The open source orchestration tool for command-line coding agents. Run Claude Code, Codex, Gemini and more side by side, see which one needs you, and answer from your phone. Windows, macOS, Linux.

Live2D、AI Agent 与 GPT-SoVITS：桌面 AI 数字角色

BioDSA: Framework for Vibe Prototyping of AI Agents for Biomedicine

基于 Spring AI 2.0 的生产级 ERP 智能助手｜Production-ready ERP AI assistant with RAG, Tool Calling, chat memory, dynamic SQL tools, multi-tenancy and ECharts.

A collection of agent trajectory analysis techniques and benchmark

A local-first workspace for chat, private knowledge, artifacts, and isolated model-driven work. Self-hosted. Provider-flexible. Apache 2.0.

Lobster0 — a self-hosted OpenClaw-inspired AI agent with persistent memory, governed autonomy, and self-evolution. 受 OpenClaw 启发的自托管 AI Agent「Lobster0」，具备持久记忆、受控自治与自我进化能力

See and manage what your coding assistants load — skills, commands, subagents, plugins and MCP servers, with real usage.

Local multi-agent harness for running persistent agent teams, long-run, society-simulation

Causal memory layer for AI agents — MCP server that records decision→outcome relationships. Survives compaction.

How AI-ready is your design system? A plug-in benchmark that runs coding agents against your component library and grades the output. Built against a production design system and generalized for any React + TypeScript component library.

Go implementation of @qdrant/fastembed.

Personal AI agent built with the eve framework — Next.js web chat + Telegram, long-term memory, receipts, and chat-created skills

An agent skill with multiple gates to check and to remove any AI slop. Use it with codex/claude code or any of your favorite AI tools.

:dog: Beagle is designed to be the unified platform for the broader Recursive Self-Improvement (RSI) ecosystem. Think of it as Hugging Face Trainer for agent evolution. Its efficient rollout engine enables evaluation and evolution at scale across different agents, datasets, benchmarks, and evolution methods.

Linux QQ 群聊 Agent（OneBot v11）：分条发言、贴纸系统、主动发言与内置运维命令